PERFORMANCE AND COMPARATIVE ANALYSIS OF INDIAN STOCK MARKET DATA USING MULTI LAYER FEED FORWARD NEURAL NETWORK AND FUZZY TIME SERIES MULTI LAYER FEED FORWARD NEURAL NETWORK MODEL WITH TRACKING SIGNAL APPROACH

This study, proposes a novel neural network and fuzzy-neural network approach for predicting the closing index of the stock market. It strives to adapt the number of hidden neurons of a Multi Layer Feed Forward Neural Network (MLFFNN) and Fuzzy Time Series Multi Layer Feed Forward Neural Network (FTS-MLFFNN) model. It uses the Tracking Signal (TS) and rejects all models which result in values outside the interval of [-4, +4]. The effectiveness of the proposed approach is verified with one step ahead of Bombay Stock Exchange (BSE100) closing stock index of Indian stock market. This novel approach reduces the over-fitting problem, reduces the neural network structure and improves prediction accuracy. In addition, the result of MLFFNN with TS approach is compared to FTS-MLFFNN with TS approach. The result indicates that the FTS-MLFFNN with TS approach outperforms the MLFFNN with TS approach.